数据集 flower_photos

 

数据预处理

INPUT_DATA = 'F://dl_dataset//flower_photos'
OUTPUT_FILE = 'flower_processed_data.npy'
training_images = []
training_labels = []
testing_images = []
testing_labels = []
validation_images = []
validation_labels = []
current_label = 0

for i in os.listdir(INPUT_DATA):
    path = os.path.join(INPUT_DATA, i).replace('//', '\\')
    if not os.path.isdir(path): continue
    for j in os.walk(path):
        for k in j[2]:
            filename = os.path.join(j[0], k)
            img = Image.open(filename)
            img = img.resize((299, 299))
            image_value = np.array(img)

             # 随机划分数据
            chance = np.random.randint(100)
            if chance < 10:
                validation_images.append(image_value)
                validation_labels.append(current_label)
            elif chance < 20:
                testing_images.append(image_value)
                testing_labels.append(current_label)
            else:
                training_images.append(image_value)
                training_labels.append(current_label)

    current_label += 1

# 将训练数据乱序
state = np.random.get_state()
np.random.shuffle(training_images)
np.random.set_state(state)
np.random.shuffle(training_labels)

out = np.asarray([training_images, training_labels,
                   validation_images, validation_labels,
                   testing_images, testing_labels])

np.save(OUTPUT_FILE, out)

存储为 npy 文件

 

迁移学习-finetune

import numpy as np
import tensorflow as tf
import tensorflow.contrib.slim as slim

# 加载通过TensorFlow-Slim定义好的inception_v3模型。
import tensorflow.contrib.slim.python.slim.nets.inception_v3 as inception_v3


INPUT_DATA = 'flower_processed_data.npy'        # 处理好之后的数据文件。
TRAIN_FILE = 'train_dir/model'              # 保存训练好的模型的路径。
CKPT_FILE = 'inception_v3.ckpt'     # 预训练模型参数

# 定义训练中使用的参数。
LEARNING_RATE = 0.0001
STEPS = 300
BATCH = 32
N_CLASSES = 5

CHECKPOINT_EXCLUDE_SCOPES = 'InceptionV3/Logits,InceptionV3/AuxLogits'      # fine_tune 参数
TRAINABLE_SCOPES = 'InceptionV3/Logits,InceptionV3/AuxLogits'   # 需要训练的网络层参数名称,在fine-tuning的过程中就是最后的全联接层。

def get_tuned_variables():
    # 获取所有需要从谷歌训练好的模型中加载的参数。
    exclusions = [scope.strip() for scope in CHECKPOINT_EXCLUDE_SCOPES.split(',')]
    variables_to_restore = []

    # 枚举inception-v3模型中所有的参数,然后判断是否需要从加载列表中移除。
    for var in slim.get_model_variables():
        excluded = False
        for exclusion in exclusions:
            if var.op.name.startswith(exclusion):
                excluded = True
                break
        if not excluded:
            variables_to_restore.append(var)
    return variables_to_restore

def get_trainable_variables():
    # 获取所有需要训练的变量列表
    scopes = [scope.strip() for scope in TRAINABLE_SCOPES.split(',')]
    variables_to_trian = []

    # 枚举所有需要训练的参数前缀,并通过这些前缀找到所有需要训练的参数。
    for scope in scopes:
        variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope)
        variables_to_trian.extend(variables)
    return variables_to_trian

def main():
    # 加载预处理好的数据。
    processed_data = np.load(INPUT_DATA)
    training_images = processed_data[0]
    training_labels = processed_data[1]
    validation_images = processed_data[2]
    validation_labels = processed_data[3]
    testing_images = processed_data[4]
    testing_labels = processed_data[5]
    n_training_example = len(training_images)

    images = tf.placeholder(tf.float32, [None, 299, 299, 3], name='input_images')
    labels = tf.placeholder(tf.int64, [None], name='labels')

    # 定义inception-v3模型。因为谷歌给出的只有模型参数取值,所以这里
    # 需要在这个代码中定义inception-v3的模型结构。虽然理论上需要区分训练和
    # 测试中使用到的模型,也就是说在测试时应该使用is_training=False,但是
    # 因为预先训练好的inception-v3模型中使用的batch normalization参数与
    # 新的数据会有出入,所以这里直接使用同一个模型来做测试。
    with slim.arg_scope(inception_v3.inception_v3_arg_scope()):
        logits, _ = inception_v3.inception_v3(images, num_classes=N_CLASSES, is_training=True)

    # 获取需要训练的变量
    trainable_variables = get_trainable_variables()

    tf.losses.softmax_cross_entropy(tf.one_hot(labels, N_CLASSES), logits, weights=1.0)
    train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(tf.losses.get_total_loss(), var_list=trainable_variables)    ### 固定部分参数,优化其他参数
    train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(tf.losses.get_total_loss())      ### 优化全部参数

    with tf.name_scope('evaluation'):
        correct_prediction = tf.equal(tf.arg_max(logits, 1), labels)        # 计算正确率
        evaluation_step = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    # 定义加载Google训练好的Inception-v3模型的Saver
    load_fn = slim.assign_from_checkpoint_fn(
        CKPT_FILE,
        get_tuned_variables(),
        ignore_missing_vars=True)

    saver = tf.train.Saver()

    with tf.Session() as sess:
        init = tf.global_variables_initializer()
        sess.run(init)
        load_fn(sess)       # 加载 预训练 参数

        start = 0
        end = BATCH
        for i in range(STEPS):
            sess.run(train_step, feed_dict={images: training_images[start: end], labels: training_labels[start: end]})

            if i % 30 == 0 or i + 1 == STEPS:
                saver.save(sess, TRAIN_FILE, global_step=i)
                validation_accuracy = sess.run(evaluation_step, feed_dict={images: validation_images, labels: validation_labels})
                print('Step %d: Validation accuracy = %.1f%%' % (i, validation_accuracy * 100.0))

            start = end
            if start == n_training_example: start = 0
            end = start + BATCH
            if end > n_training_example: end = n_training_example

        # 在最后的测试数据上测试正确率
        test_accuracy = sess.run(evaluation_step, feed_dict={images: testing_images, labels: testing_labels})
        print('Final test accuracy = %.1f%%' % (test_accuracy * 100))


if __name__ == '__main__':
    main()

 

全部更新,训练慢,但是效果还行

Step 0: Validation accuracy = 25.6%
Step 30: Validation accuracy = 26.4%
Step 60: Validation accuracy = 48.0%
Step 90: Validation accuracy = 79.3%
Step 120: Validation accuracy = 88.6%
Step 150: Validation accuracy = 92.3%
Step 180: Validation accuracy = 93.2%
Step 210: Validation accuracy = 96.0%
Step 240: Validation accuracy = 94.9%
Step 270: Validation accuracy = 94.6%
Step 299: Validation accuracy = 94.6%
Final test accuracy = 92.4%

 

部分更新,训练快,但是效果不行,当然你可以继续训练看看效果

Step 0: Validation accuracy = 25.0%
Step 30: Validation accuracy = 25.3%
Step 60: Validation accuracy = 30.1%
Step 90: Validation accuracy = 32.7%
Step 120: Validation accuracy = 42.0%
Step 150: Validation accuracy = 52.8%
Step 180: Validation accuracy = 53.7%
Step 210: Validation accuracy = 59.7%
Step 240: Validation accuracy = 61.9%
Step 270: Validation accuracy = 66.5%
Step 299: Validation accuracy = 67.0%
Final test accuracy = 67.0%

 

 

参考资料: 

https://www.jianshu.com/p/0237ebbee5d5

https://www.jianshu.com/p/a4fbe308b7b8